Pig weight estimation device and weight estimation method based on 3D convolutional neural network

Abstract

The invention discloses a pig weight estimation device and method based on a 3D convolutional neural network. The pig weight estimation device comprises a pig fence; by arranging a face recognition device and an ear tag recognition device on one side of the pig fence, when a pig stands on one side of the face recognition device, a recognition camera can shoot a picture of the face of the pig, then the picture is compared with pig features stored in a feature data box, and the identity and the label of the current pig are found out; the rotating motor can enable the recognition camera and the feature data box to rotate, the recognition camera can rotate along with the face of a pig, the face picture of the pig can be conveniently collected, if face feature scanning fails, the ear tag sensing gun can be used for sensing the ear tag of the pig, and the magnetic chip is arranged in the ear tag of the pig, so that the ear tag can be conveniently recognized. The magnetic chip can store the information and the label of the current pig, and the pig is put into the pig fence to estimate the weight after the identity of the pig is successfully identified, so that the weight of each pig can be conveniently recorded and estimated.

Description

technical field [0001] The invention belongs to the technical field of pig weight estimation, and in particular relates to a pig weight estimation device and method based on a 3D convolutional neural network. Background technique [0002] The pig industry is an important industry in my country's agriculture and plays an important role in ensuring the safe supply of meat and food. At present, my country's pig industry is transforming from the traditional pig industry to the modern pig industry. Production capacity is changing significantly. [0003] However, during the breeding process of pigs, the staff need to estimate the weight of the pigs to judge the growth of the pigs. Most of the weight estimates of pigs are manually observed by naked eyes, which leads to low efficiency of weight estimation, and the weight estimation data and The actual data differs too much, and it is not convenient to record pig information and weight estimation data, so a pig weight estimation devi...

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to overcome the existing defects and provide a weight estimation device and method for pigs based on 3D convolutional neural network, so as to solve the problem that the staff in the breeding process of pigs proposed in the above-mentioned background technology need to The weight of pigs is estimated to judge the growth of pigs. Most of the weight estimates of pigs are manually observed by naked eyes, which leads to low efficiency of weight estimation, and the difference between estimated weight data and actual data is too large, which is not convenient for pig information and the recording of estimated weight data

Images